💻 Qwopus3.5-4B-Coder-Fable5-v1 GGUF
GGUF builds for llama.cpp, LM Studio, and local inference
Fable-5 traces · agentic coding · tool use · debugging
Overview
Qwopus3.5-4B-Coder-Fable5-v1 is a Fable-5 trace continuation of
Jackrong/Qwopus3.5-4B-Coder.
The base model, Qwopus3.5-4B-Coder, is a compact Qwen3.5-based coding model trained for reasoning, tool use, function calling, coding workflows, and agent-style behavior.
This release continues that model on
Glint-Research/Fable-5-traces, a dataset of Claude Fable 5 local coding-agent traces. The dataset is heavily oriented around tool-use trajectories, repository work, local command context, code editing, debugging loops, and
<think>-style reasoning completions.
The result is a small local coding-agent model intended for:
| Area | Description |
|---|
| Tool-use workflows | Bash, Read, Write, Edit, repo inspection, and action traces. |
| Debugging | Failing tests, stack traces, root-cause analysis, and patch planning. |
| Trace-style reasoning | Long-form planning and <think> style reasoning traces. |
| Local agents | Hermes-style, Claude-Code-style, OpenCode-style, and LM Studio workflows. |
Files
Typical GGUF files:
Qwopus3.5-4B-Coder-Fable5-v1-Q4_K_M.ggufQwopus3.5-4B-Coder-Fable5-v1-Q5_K_M.ggufQwopus3.5-4B-Coder-Fable5-v1-mmproj-BF16.gguf
Which file should I use?
| File | Use case |
|---|
Q4_K_M | Best default. Small, fast, good quality. |
Q5_K_M | Better quality while still compact. |
Q8_0 | Higher quality, larger memory use, if included. |
mmproj-BF16 | Multimodal projector for compatible runtimes. |
llama.cpp
1llama-cli \
2 -m Qwopus3.5-4B-Coder-Fable5-v1-Q5_K_M.gguf \
3 -p "Write a Bash/Read/Edit style plan for debugging a failing Python repo." \
4 -n 768 \
5 --temp 0.7 \
6 --top-p 0.95
llama.cpp Server
1llama-server \
2 -m Qwopus3.5-4B-Coder-Fable5-v1-Q5_K_M.gguf \
3 --host 0.0.0.0 \
4 --port 8080 \
5 --ctx-size 8192
Then call it with an OpenAI-compatible client:
1curl -X POST "http://localhost:8080/v1/chat/completions" \
2 -H "Content-Type: application/json" \
3 --data '{
4 "model": "Qwopus3.5-4B-Coder-Fable5-v1-Q5_K_M.gguf",
5 "messages": [
6 {"role": "user", "content": "Write a tool-use plan for debugging a Python repo."}
7 ],
8 "temperature": 0.7,
9 "top_p": 0.95
10 }'
About the Fable-5 Traces
Glint-Research/Fable-5-traces contains Claude Fable 5 coding traces.
The dataset includes fields such as:
1uid
2source_file
3session
4model
5context
6cot
7output_type
8output
9completion
10origin
The examples are not simple chat pairs. They are multi-step agent trajectories with local development context, reasoning traces, and tool-use outputs.
Common patterns in the dataset include:
- user coding requests
- local-command caveats
- repository inspection
- Bash command usage
- file reads
- file writes
- edits
- debugging passes
- playtesting / validation loops
<think>...</think> reasoning traces- tool-use completions
A large portion of the dataset is tool_use style data, which makes it especially relevant for local coding agents and developer automation.
Capabilities
Agentic coding
Designed for coding-agent loops where the model must inspect a repo, plan work, call tools, edit files, and validate changes.
Tool-use style outputs
Works well with prompts that expose structured tools such as:
1Bash
2Read
3Write
4Edit
5Search
6Grep
Debugging and repair
Useful for:
- finding likely failing files
- explaining stack traces
- planning test commands
- proposing minimal patches
- iterating after errors
Local-first deployment
The release includes Transformers, GGUF, MLX, and MLX 4-bit formats so it can run in Python, llama.cpp, LM Studio, and Apple Silicon workflows.
Available Releases
Credits
Built on:
Jackrong/Qwopus3.5-4B-Coder by JackrongGlint-Research/Fable-5-traces by Glint-Research- Qwen / Qwen3.5 model family
- Unsloth
- Hugging Face
- llama.cpp
- mlx-lm
